Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
GUI reasoning on GUI-Act-Web
Loading...
87.73
Type Success Rate
CAPO
54.8348
63.3749
71.915
80.4551
Dec 2, 2025
Type Success Rate
Goal Success Rate (GR)
Step Success Rate (SR)
Updated 3d ago
Evaluation Results
Method
Method
Links
Type Success Rate
Goal Success Rate (GR)
Step Success Rate (SR)
CAPO
Prompting=zero-shot
2025.12
87.73
85.85
85.85
GRPO
Prompting=zero-shot
2025.12
85.1
82.36
70.23
Os-Atlas-4B
Prompting=zero-shot
2025.12
79.22
58.57
42.62
QwenVL2.5-3B
Prompting=zero-shot
2025.12
56.1
64.28
55.61
Feedback
Search any
task
Search any
task